From d2373862b3589260f0139a6e4969478f84154369 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:43 +0200 Subject: [PATCH 1/6] inet: frags: use INC_STATS_BH in the ipv6 reassembly code Softirqs are already disabled so no need to do it again, thus let's be consistent and use the IP6_INC_STATS_BH variant. Signed-off-by: Nikolay Aleksandrov Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/reassembly.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index f1709c4a289a..512ccc027ce3 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -355,8 +355,8 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, discard_fq: inet_frag_kill(&fq->q, &ip6_frags); err: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; } @@ -566,7 +566,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return -1; fail_hdr: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; } From 06aa8b8a0345c78f4d9a1fb3f852952b12a0e40c Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:44 +0200 Subject: [PATCH 2/6] inet: frags: rename last_in to flags The last_in field has been used to store various flags different from first/last frag in so give it a more descriptive name: flags. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- net/ieee802154/reassembly.c | 14 +++++++------- net/ipv4/inet_fragment.c | 14 +++++++------- net/ipv4/ip_fragment.c | 20 ++++++++++---------- net/ipv6/netfilter/nf_conntrack_reasm.c | 12 ++++++------ net/ipv6/reassembly.c | 18 +++++++++--------- 6 files changed, 40 insertions(+), 40 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 6f4930a0b660..5024d6c20407 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -25,7 +25,7 @@ struct inet_frag_queue { ktime_t stamp; int len; /* total length of orig datagram */ int meat; - __u8 last_in; /* first/last segment arrived? */ + __u8 flags; /* first/last segment arrived? */ #define INET_FRAG_EVICTED 8 #define INET_FRAG_COMPLETE 4 diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c index f13d4f32e207..5607accd2fee 100644 --- a/net/ieee802154/reassembly.c +++ b/net/ieee802154/reassembly.c @@ -99,7 +99,7 @@ static void lowpan_frag_expire(unsigned long data) spin_lock(&fq->q.lock); - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q, &lowpan_frags); @@ -142,7 +142,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, struct net_device *dev; int end, offset; - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = lowpan_cb(skb)->d_offset << 3; @@ -154,14 +154,14 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) + if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } @@ -201,13 +201,13 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, if (frag_type == LOWPAN_DISPATCH_FRAG1) { /* Calculate uncomp. 6lowpan header to estimate full size */ fq->q.meat += lowpan_uncompress_size(skb, NULL); - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } else { fq->q.meat += skb->len; } add_frag_mem_limit(&fq->q, skb->truesize); - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 62b1f73749dc..e3ebc6608e5d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -152,8 +152,8 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) } /* suppress xmit of (icmp) error packet */ - fq->last_in &= ~INET_FRAG_FIRST_IN; - fq->last_in |= INET_FRAG_EVICTED; + fq->flags &= ~INET_FRAG_FIRST_IN; + fq->flags |= INET_FRAG_EVICTED; hlist_del(&fq->list); hlist_add_head(&fq->list, &expired); ++evicted; @@ -289,16 +289,16 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) if (del_timer(&fq->timer)) atomic_dec(&fq->refcnt); - if (!(fq->last_in & INET_FRAG_COMPLETE)) { + if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); atomic_dec(&fq->refcnt); - fq->last_in |= INET_FRAG_COMPLETE; + fq->flags |= INET_FRAG_COMPLETE; } } EXPORT_SYMBOL(inet_frag_kill); static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb) + struct sk_buff *skb) { if (f->skb_free) f->skb_free(skb); @@ -311,7 +311,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) struct netns_frags *nf; unsigned int sum, sum_truesize = 0; - WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); + WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ @@ -349,7 +349,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, if (qp->net == nf && f->match(qp, arg)) { atomic_inc(&qp->refcnt); spin_unlock(&hb->chain_lock); - qp_in->last_in |= INET_FRAG_COMPLETE; + qp_in->flags |= INET_FRAG_COMPLETE; inet_frag_put(qp_in, f); return qp; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 634fc31aa243..6fce1ecc5bca 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -185,16 +185,16 @@ static void ip_expire(unsigned long arg) spin_lock(&qp->q.lock); - if (qp->q.last_in & INET_FRAG_COMPLETE) + if (qp->q.flags & INET_FRAG_COMPLETE) goto out; ipq_kill(qp); - if (!(qp->q.last_in & INET_FRAG_EVICTED)) + if (!(qp->q.flags & INET_FRAG_EVICTED)) IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { + if ((qp->q.flags & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; @@ -302,7 +302,7 @@ static int ip_frag_reinit(struct ipq *qp) } while (fp); sub_frag_mem_limit(&qp->q, sum_truesize); - qp->q.last_in = 0; + qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.fragments = NULL; @@ -323,7 +323,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) int err = -ENOENT; u8 ecn; - if (qp->q.last_in & INET_FRAG_COMPLETE) + if (qp->q.flags & INET_FRAG_COMPLETE) goto err; if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && @@ -350,9 +350,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * or have different end, the segment is corrupted. */ if (end < qp->q.len || - ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len)) + ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) goto err; - qp->q.last_in |= INET_FRAG_LAST_IN; + qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { if (end&7) { @@ -362,7 +362,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ - if (qp->q.last_in & INET_FRAG_LAST_IN) + if (qp->q.flags & INET_FRAG_LAST_IN) goto err; qp->q.len = end; } @@ -471,13 +471,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) qp->ecn |= ecn; add_frag_mem_limit(&qp->q, skb->truesize); if (offset == 0) - qp->q.last_in |= INET_FRAG_FIRST_IN; + qp->q.flags |= INET_FRAG_FIRST_IN; if (ip_hdr(skb)->frag_off & htons(IP_DF) && skb->len + ihl > qp->q.max_size) qp->q.max_size = skb->len + ihl; - if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { unsigned long orefdst = skb->_skb_refdst; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 3d4bccf6d67d..cca686e42b97 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -222,7 +222,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, int offset, end; u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) { + if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } @@ -253,11 +253,11 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) { + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -272,7 +272,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) { + if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } @@ -354,7 +354,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } return 0; @@ -617,7 +617,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) goto ret_orig; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { ret_skb = nf_ct_frag6_reasm(fq, dev); if (ret_skb == NULL) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 512ccc027ce3..b4baceed0d0d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -131,7 +131,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, spin_lock(&fq->q.lock); - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q, frags); @@ -141,13 +141,13 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, if (!dev) goto out_rcu_unlock; - if (!(fq->q.last_in & INET_FRAG_EVICTED)) + if (!(fq->q.flags & INET_FRAG_EVICTED)) IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); /* Don't send error if the first segment did not arrive. */ - if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) + if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments) goto out_rcu_unlock; /* @@ -209,7 +209,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct net *net = dev_net(skb_dst(skb)->dev); u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = ntohs(fhdr->frag_off) & ~0x7; @@ -240,9 +240,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -260,7 +260,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) + if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } @@ -335,10 +335,10 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; From 1ab1934ed80aa90b268a62a561f8fdc60812793c Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:45 +0200 Subject: [PATCH 3/6] inet: frags: enum the flag definitions and add descriptions Move the flags to an enum definion, swap FIRST_IN/LAST_IN to be in increasing order and add comments explaining each flag and the inet_frag_queue struct members. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/inet_frag.h | 46 +++++++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 11 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5024d6c20407..90015c47b447 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -15,25 +15,49 @@ struct netns_frags { int low_thresh; }; +/** + * fragment queue flags + * + * @INET_FRAG_FIRST_IN: first fragment has arrived + * @INET_FRAG_LAST_IN: final fragment has arrived + * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction + * @INET_FRAG_EVICTED: frag queue is being evicted + */ +enum { + INET_FRAG_FIRST_IN = BIT(0), + INET_FRAG_LAST_IN = BIT(1), + INET_FRAG_COMPLETE = BIT(2), + INET_FRAG_EVICTED = BIT(3) +}; + +/** + * struct inet_frag_queue - fragment queue + * + * @lock: spinlock protecting the queue + * @timer: queue expiration timer + * @list: hash bucket list + * @refcnt: reference count of the queue + * @fragments: received fragments head + * @fragments_tail: received fragments tail + * @stamp: timestamp of the last received fragment + * @len: total length of the original datagram + * @meat: length of received fragments so far + * @flags: fragment queue flags + * @max_size: (ipv4 only) maximum received fragment size with IP_DF set + * @net: namespace that this frag belongs to + */ struct inet_frag_queue { spinlock_t lock; - struct timer_list timer; /* when will this queue expire? */ + struct timer_list timer; struct hlist_node list; atomic_t refcnt; - struct sk_buff *fragments; /* list of received fragments */ + struct sk_buff *fragments; struct sk_buff *fragments_tail; ktime_t stamp; - int len; /* total length of orig datagram */ + int len; int meat; - __u8 flags; /* first/last segment arrived? */ - -#define INET_FRAG_EVICTED 8 -#define INET_FRAG_COMPLETE 4 -#define INET_FRAG_FIRST_IN 2 -#define INET_FRAG_LAST_IN 1 - + __u8 flags; u16 max_size; - struct netns_frags *net; }; From f926e23660d52601089222cb4755aabc693ca390 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:46 +0200 Subject: [PATCH 4/6] inet: frags: fix function declaration alignments in inet_fragment Fix a couple of functions' declaration alignments. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/inet_fragment.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index e3ebc6608e5d..fa49916c23a0 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -334,8 +334,9 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) EXPORT_SYMBOL(inet_frag_destroy); static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, - struct inet_frag_queue *qp_in, struct inet_frags *f, - void *arg) + struct inet_frag_queue *qp_in, + struct inet_frags *f, + void *arg) { struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f); struct inet_frag_queue *qp; @@ -368,7 +369,8 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, - struct inet_frags *f, void *arg) + struct inet_frags *f, + void *arg) { struct inet_frag_queue *q; @@ -393,7 +395,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - struct inet_frags *f, void *arg) + struct inet_frags *f, + void *arg) { struct inet_frag_queue *q; @@ -405,7 +408,8 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, } struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, - struct inet_frags *f, void *key, unsigned int hash) + struct inet_frags *f, void *key, + unsigned int hash) { struct inet_frag_bucket *hb; struct inet_frag_queue *q; From 2e404f632f44979ddf0ce0808a438249a72d7015 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:47 +0200 Subject: [PATCH 5/6] inet: frags: use INET_FRAG_EVICTED to prevent icmp messages Now that we have INET_FRAG_EVICTED we might as well use it to stop sending icmp messages in the "frag_expire" functions instead of stripping INET_FRAG_FIRST_IN from their flags when evicting. Also fix the comment style in ip6_expire_frag_queue(). Signed-off-by: Nikolay Aleksandrov Reviewed-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv4/inet_fragment.c | 2 -- net/ipv4/ip_fragment.c | 14 +++++++------- net/ipv6/reassembly.c | 15 ++++++++------- 3 files changed, 15 insertions(+), 16 deletions(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index fa49916c23a0..4baa76c60398 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -151,8 +151,6 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) goto evict_again; } - /* suppress xmit of (icmp) error packet */ - fq->flags &= ~INET_FRAG_FIRST_IN; fq->flags |= INET_FRAG_EVICTED; hlist_del(&fq->list); hlist_add_head(&fq->list, &expired); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 6fce1ecc5bca..cb56bcc1eee2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -189,16 +189,18 @@ static void ip_expire(unsigned long arg) goto out; ipq_kill(qp); - - if (!(qp->q.flags & INET_FRAG_EVICTED)) - IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if ((qp->q.flags & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { + if (!(qp->q.flags & INET_FRAG_EVICTED)) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); + + if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments) + goto out; + rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) @@ -211,8 +213,7 @@ static void ip_expire(unsigned long arg) if (err) goto out_rcu_unlock; - /* - * Only an end host needs to send an ICMP + /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ if (qp->user == IP_DEFRAG_AF_PACKET || @@ -221,7 +222,6 @@ static void ip_expire(unsigned long arg) (skb_rtable(head)->rt_type != RTN_LOCAL))) goto out_rcu_unlock; - /* Send an ICMP "Fragment Reassembly Timeout" message. */ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); out_rcu_unlock: diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index b4baceed0d0d..beb6872a8fa5 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -141,19 +141,20 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, if (!dev) goto out_rcu_unlock; - if (!(fq->q.flags & INET_FRAG_EVICTED)) - IP6_INC_STATS_BH(net, __in6_dev_get(dev), - IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + if (fq->q.flags & INET_FRAG_EVICTED) + goto out_rcu_unlock; + + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + /* Don't send error if the first segment did not arrive. */ if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments) goto out_rcu_unlock; - /* - But use as source device on which LAST ARRIVED - segment was received. And do not use fq->dev - pointer directly, device might already disappeared. + /* But use as source device on which LAST ARRIVED + * segment was received. And do not use fq->dev + * pointer directly, device might already disappeared. */ fq->q.fragments->dev = dev; icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); From d4ad4d22e7ac6b8711b35d7e86eb29f03f8ac153 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 1 Aug 2014 12:29:48 +0200 Subject: [PATCH 6/6] inet: frags: use kmem_cache for inet_frag_queue Use kmem_cache to allocate/free inet_frag_queue objects since they're all the same size per inet_frags user and are alloced/freed in high volumes thus making it a perfect case for kmem_cache. Signed-off-by: Nikolay Aleksandrov Acked-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 4 +++- net/ieee802154/reassembly.c | 7 ++++++- net/ipv4/inet_fragment.c | 13 ++++++++++--- net/ipv4/ip_fragment.c | 5 ++++- net/ipv6/netfilter/nf_conntrack_reasm.c | 8 ++++++-- net/ipv6/reassembly.c | 7 ++++++- 6 files changed, 35 insertions(+), 9 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 90015c47b447..65a8855e99fe 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -101,9 +101,11 @@ struct inet_frags { void (*destructor)(struct inet_frag_queue *); void (*skb_free)(struct sk_buff *); void (*frag_expire)(unsigned long data); + struct kmem_cache *frags_cachep; + const char *frags_cache_name; }; -void inet_frags_init(struct inet_frags *); +int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); void inet_frags_init_net(struct netns_frags *nf); diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c index 5607accd2fee..ffec6ce51005 100644 --- a/net/ieee802154/reassembly.c +++ b/net/ieee802154/reassembly.c @@ -30,6 +30,8 @@ #include "reassembly.h" +static const char lowpan_frags_cache_name[] = "lowpan-frags"; + struct lowpan_frag_info { __be16 d_tag; u16 d_size; @@ -571,7 +573,10 @@ int __init lowpan_net_frag_init(void) lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.match = lowpan_frag_match; lowpan_frags.frag_expire = lowpan_frag_expire; - inet_frags_init(&lowpan_frags); + lowpan_frags.frags_cache_name = lowpan_frags_cache_name; + ret = inet_frags_init(&lowpan_frags); + if (ret) + goto err_pernet; return ret; err_pernet: diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4baa76c60398..9eb89f3f0ee4 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -198,7 +198,7 @@ static void inet_frag_schedule_worker(struct inet_frags *f) schedule_work(&f->frags_work); } -void inet_frags_init(struct inet_frags *f) +int inet_frags_init(struct inet_frags *f) { int i; @@ -213,6 +213,12 @@ void inet_frags_init(struct inet_frags *f) seqlock_init(&f->rnd_seqlock); f->last_rebuild_jiffies = 0; + f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, + NULL); + if (!f->frags_cachep) + return -ENOMEM; + + return 0; } EXPORT_SYMBOL(inet_frags_init); @@ -225,6 +231,7 @@ EXPORT_SYMBOL(inet_frags_init_net); void inet_frags_fini(struct inet_frags *f) { cancel_work_sync(&f->frags_work); + kmem_cache_destroy(f->frags_cachep); } EXPORT_SYMBOL(inet_frags_fini); @@ -327,7 +334,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) if (f->destructor) f->destructor(q); - kfree(q); + kmem_cache_free(f->frags_cachep, q); } EXPORT_SYMBOL(inet_frag_destroy); @@ -377,7 +384,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, return NULL; } - q = kzalloc(f->qsize, GFP_ATOMIC); + q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (q == NULL) return NULL; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index cb56bcc1eee2..15f0e2bad7ad 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -55,6 +55,7 @@ */ static int sysctl_ipfrag_max_dist __read_mostly = 64; +static const char ip_frag_cache_name[] = "ip4-frags"; struct ipfrag_skb_cb { @@ -860,5 +861,7 @@ void __init ipfrag_init(void) ip4_frags.qsize = sizeof(struct ipq); ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; - inet_frags_init(&ip4_frags); + ip4_frags.frags_cache_name = ip_frag_cache_name; + if (inet_frags_init(&ip4_frags)) + panic("IP: failed to allocate ip4_frags cache\n"); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index cca686e42b97..6f187c8d8a1b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -50,6 +50,7 @@ #include #include +static const char nf_frags_cache_name[] = "nf-frags"; struct nf_ct_frag6_skb_cb { @@ -677,12 +678,15 @@ int nf_ct_frag6_init(void) nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; - inet_frags_init(&nf_frags); - + nf_frags.frags_cache_name = nf_frags_cache_name; + ret = inet_frags_init(&nf_frags); + if (ret) + goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); +out: return ret; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index beb6872a8fa5..c6557d9f7808 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -60,6 +60,8 @@ #include #include +static const char ip6_frag_cache_name[] = "ip6-frags"; + struct ip6frag_skb_cb { struct inet6_skb_parm h; @@ -748,7 +750,10 @@ int __init ipv6_frag_init(void) ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; - inet_frags_init(&ip6_frags); + ip6_frags.frags_cache_name = ip6_frag_cache_name; + ret = inet_frags_init(&ip6_frags); + if (ret) + goto err_pernet; out: return ret;